logo Idiap Research Institute        
 [BibTeX] [Marc21]
SVR vs MLP for Phone Duration Modelling in HMM-based Speech Synthesis
Type of publication: Conference paper
Citation: Lazaridis_SP-7_2014
Publication status: Published
Booktitle: Speech Prosody
Year: 2014
Crossref: Lazaridis_Idiap-RR-03-2014:
Abstract: In this paper we investigate external phone duration models (PDMs) for improving the quality of synthetic speech in hidden Markov model (HMM)-based speech synthesis. Support Vector Regression (SVR) and Multilayer Perceptron (MLP) were used for this task. SVR and MLP PDMs were compared with the explicit duration modelling of hidden semi-Markov models (HSMMs). Experiments done on an American English database showed the SVR outperforming the MLP and HSMM duration modelling on objective and subjective evaluation. In the objective test, SVR managed to outperform MLP and HSMM models achieving 15.3% and 25.09% relative improvement in terms of root mean square error (RMSE) respectively. Moreover, in the subjective evaluation test, on synthesized speech, the SVR model was preferred over the MLP and HSMMmodels, achieving a preference score of 35.93% and 56.30%, respectively.
Keywords: HMM-based speech synthesis, HSMM explicit duration modelling, multilayer perceptron, phone duration modelling, Support Vector Regression
Projects Idiap
Authors Lazaridis, Alexandros
Honnet, Pierre-Edouard
Garner, Philip N.
Added by: [UNK]
Total mark: 0
  • Lazaridis_SP-7_2014.pdf